面向Kinect运动数据的鲁棒足迹检测

Robust foot plant detection for Kinect-captured motion data

目的 Kinect可实时获取运动数据且较传统的运动捕捉设备采集成本低廉,在运动数据捕捉方面得到了广泛应用。但Kinect获取的运动数据精度较低,现有运动数据处理算法难以适用。方法针对运动数据处理的关键步骤足迹检测问题,提出面向Kinect运动数据的鲁棒足迹检测算法。首先使用自适应的双边滤波算法降低Kinect运动数据中的噪声;其次定义多种脚部运动特征并用于分类,优化分类效果;最后使用支持向量机(SVM)算法训练决策函数并用于足迹检测。结果本文算法应用于多种类型运动数据后,可以有效地减少Kinect运动数据中的噪声,足迹检测的时间性能以及准确性良好,其中足迹检测的准确率比经典的基准线方法提高了10%左右,比K近邻方法提高了8%左右,检测一帧运动足迹的速度为K近邻方法的7倍左右。结论对实验结果的分析证明算法具有良好的鲁棒性、时间性能以及准确率,可广泛应用于运动数据的处理之中。

Objective Kinect can be utilized to capture motion data in real time. Given that its cost is lower than that of tra- ditional motion-capture devices, Kinect is widely used to capture motion data. However, the noise in Kinect-captured mo- tion data makes the quality of motion data relatively unsatisfactory. Thus, previous data-processing methods failed to handle such data well. Method Foot plant detection is a key procedure in motion editing; it detects whether the character＇s foot is on the ground. A robust foot plant detection algorithm for Kinect-captured motion data is proposed in this study. First, an adaptively bilateral filtering method is proposed to reduce the noise in Kinect-captured motion data. Second, muhiple fea- tures of the motion data are defined and utilized to optimize the effect of foot plant detection. Finally, a decision function is trained with the support vector machine algorithm and applied to foot plant detection. Result After being applied to a data- set that consists of various types of motion, the noise in the Kinect-captured motion data was reduced effectively. The accu- racy of foot plant detection increased by 6% after applying the proposed adaptively bilateral filtering method. Good time performance and high accuracy of foot plant detection were acquired as well. The foot plant detection accuracy of the pro- posed detection algorithm increased by 11% and 8% compared with that of the baseline method and the K nearest-neighbor method, respectively. The time consumed in the detection of the motion data of one frame is a seventh of that of the K nea- rest-neighbor method. Conclusion Experimental results proved the effectiveness and robustness of the proposed foot plant detection algorithm. Thus, this algorithm can be widely utilized in motion data processing.